文献データベース

EIM-TRNG: Obfuscating Deep Neural Network Weights with Encoding-in-Memory True Random Number Generator via RowHammer

Authors: Ranyang Zhou, Abeer Matar A. Almalky, Gamana Aragonda, Sabbir Ahmed, Filip Roth Trønnes-Christensen, Adnan Siraj Rakin, Shaahin Angizi | Published: 2025-07-03
DRAMベースのTRNG
トリガーの検知
ハードウェア設計

Empowering Manufacturers with Privacy-Preserving AI Tools: A Case Study in Privacy-Preserving Machine Learning to Solve Real-World Problems

Authors: Xiaoyu Ji, Jessica Shorland, Joshua Shank, Pascal Delpe-Brice, Latanya Sweeney, Jan Allebach, Ali Shakouri | Published: 2025-07-02
医療画像分析
画像処理手法
製品安全性

Tuning without Peeking: Provable Privacy and Generalization Bounds for LLM Post-Training

Authors: Ismail Labiad, Mathurin Videau, Matthieu Kowalski, Marc Schoenauer, Alessandro Leite, Julia Kempe, Olivier Teytaud | Published: 2025-07-02
RAG
プライバシー保証
差分プライバシー

Graph Representation-based Model Poisoning on Federated LLMs in CyberEdge Networks

Authors: Hanlin Cai, Haofan Dong, Houtianfu Wang, Kai Li, Ozgur B. Akan | Published: 2025-07-02
プロンプトインジェクション
ポイズニング攻撃
悪意のあるクライアント

A Privacy-Preserving Indoor Localization System based on Hierarchical Federated Learning

Authors: Masood Jan, Wafa Njima, Xun Zhang | Published: 2025-07-02
プライバシー保証
分散学習
性能評価

SafePTR: Token-Level Jailbreak Defense in Multimodal LLMs via Prune-then-Restore Mechanism

Authors: Beitao Chen, Xinyu Lyu, Lianli Gao, Jingkuan Song, Heng Tao Shen | Published: 2025-07-02
プロンプトインジェクション
脱獄攻撃手法
透明性と検証

ICLShield: Exploring and Mitigating In-Context Learning Backdoor Attacks

Authors: Zhiyao Ren, Siyuan Liang, Aishan Liu, Dacheng Tao | Published: 2025-07-02
ICL防御メカニズム
トリガーの検知
バックドア攻撃手法

Gaze3P: Gaze-Based Prediction of User-Perceived Privacy

Authors: Mayar Elfares, Pascal Reisert, Ralf Küsters, Andreas Bulling | Published: 2025-07-01 | Updated: 2025-09-10
プライバシー手法
プライバシー評価
研究方法論

Are AI-Generated Fixes Secure? Analyzing LLM and Agent Patches on SWE-bench

Authors: Amirali Sajadi, Kostadin Damevski, Preetha Chatterjee | Published: 2025-06-30 | Updated: 2025-07-24
ソフトウェアセキュリティ
プロンプトインジェクション
大規模言語モデル

AI Risk-Management Standards Profile for General-Purpose AI (GPAI) and Foundation Models

Authors: Anthony M. Barrett, Jessica Newman, Brandie Nonnecke, Nada Madkour, Dan Hendrycks, Evan R. Murphy, Krystal Jackson, Deepika Raman | Published: 2025-06-30
モデルインバージョン
リスク評価手法
教育やフォローアップ